• Smart Media Journal
• /
• v.12 no.6
• /
• pp.35-40
• /
• 2023

In this study paper, we examine pre-trained language models used in Multi-Goal Conversational Recommender Systems (MG-CRS), comparing and analyzing their performances of various pre-trained language models. Specifically, we investigates the impact of the sizes of language models on the performance of MG-CRS. The study targets three types of language models - of BERT, GPT2, and BART, and measures and compares their accuracy in two tasks of 'type prediction' and 'topic prediction' on the MG-CRS dataset, DuRecDial 2.0. Experimental results show that all models demonstrated excellent performance in the type prediction task, but there were notable provide significant performance differences in performance depending on among the models or based on their sizes in the topic prediction task. Based on these findings, the study provides directions for improving the performance of MG-CRS.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.84-86
• /
• 2022

Task-oriented chatbots prevail in various filed with the artificial intelligent dialogue system. The need for chatbots in customer services is growing, especially in education businesses given that there are many user inquiries and consultation requests. However, current dialogue systems only function as simple reactions or predetermined and frequently used actions. Meanwhile, the research about customized recommendation systems through artificial intelligence is very active with a wide variety of educational content. Although a dialogue system and a recommendation system is a core element in this domain, it has a limitation in that it is being conducted separately. Therefore, we present a study on a recommendation system that can recommend user-customized lectures combined with a dialogue system. With this combination, our system can respond to additional functions beyond these limitations. Through our research, we expect that work efficiency and user satisfaction will be improved by applying chatbots in education domains that are becoming more diversified and personalized.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.464-465
• /
• 2023

대화형 추천 시스템은 대화를 통해 사용자의 현재 선호도를 파악하고 상품을 추천해주는 시스템이다. 대화의 맥락은 변화하기 때문에 대화 중 최근 언급된 엔티티가 사용자의 현재 선호와 더 관련이 있다. 그러나, 기존 방법들은 언급된 엔티티들의 순서를 고려하지 않았기 때문에 사용자의 현재 선호도를 표현하는데 한계가 존재한다. 본 논문에서는, 대화 내 언급된 엔티티들의 순서를 고려하는 아키텍처를 제안하고, 실세계 데이터를 활용해 다음 상품을 예측하는데 엔티티 순서를 고려하는 것이 효과적인지 실험을 통해 보여준다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.466-467
• /
• 2023

다중 목표 대화형 추천 시스템에서 대화의 흐름을 관리하기 위해 사용되는 목표설정을 한다. 본 논문에서는 목표 예측을 위해 기존에 사용되던 입력 프롬프트를 더욱 정교한 형태로 만들어보는 것이 목표 예측 정확도 향상과 더 나아가 응답 생성에도 도움이 되는지 사전 실험을 통해 당위성을 보여준다

• Proceedings of the KAIS Fall Conference
• /
• 2008.11a
• /
• pp.21-24
• /
• 2008

본 논문에서는 오프라인 쇼핑몰에서 위치추적 기술과 동선분석을 이용하여 오프라인 쇼핑몰 고객의 위치분석 데이터를 분석한 결과를 토대로 고객에게 실시간 대화형(Interactive) 서비스 제공을 위한 선호 상품 시스템을 설계하여 쇼핑효과를 극대화하며, 고객 만족도를 향상시킬 수 있도록 돕는데 그 목적이 있다.

• Proceedings of the KAIS Fall Conference
• /
• 2010.05a
• /
• pp.539-542
• /
• 2010

본 논문에서는 오프라인 쇼핑몰에서 위치추적 기술과 동선분석을 이용하여 오프라인 쇼핑몰 고객의 위치분석 데이터를 분석한 결과를 토대로 고객에게 실시간 대화형(Interactive) 서비스 제공을 위한 선호 상품 시스템을 설계하여 쇼핑효과를 극대화하며, 고객 만족도를 향상시킬 수 있도록 돕는데 그 목적이 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.543-550
• /
• 2020

Interest in food recipe retrieval systems has been increasing recently. Most computer-based recipe retrieval systems are searched by cooking name or ingredient name. Since each recipe provides information in different weighing units, recalculations to the desired amount are necessary and inconvenient. This paper introduces a computer system that addresses these inconveniences. The system is a chatbot system, based on web-based recipe recommendations, for users familiar with the use of messenger conversation systems. After selecting the most popular recipes by their names, and pre-processing to extract only information required for the recipes, the system recommends recipes based on the 100,000 data. Recipes are then searched by the names of food ingredients (included and excluded). Recalculations are performed based on the number of servings entered by the user. A satisfaction rate for the systems' recommendations was 90.5%.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.303-308
• /
• 2022

A chatbot is a responsive chatting program that can communicate with people through text or voice. 'Siri' and 'Bixby' installed in smartphones are also representative artificial intelligences that use the chatbot system. With the rapid development of chatbots, users in various fields have also begun to pay attention to the food service industry. As machine learning technology developed, it became possible to use more flexible conversations, and it soon expanded to the realm of education. Userㄴs interact through conversations with chatbots, and active interactions stimulate users' desires and at the same time have a positive effect on learning motivation. Recommendation system programs using chatbots not only recommend products according to users' preferences, but also provide various additional information. This study planned a program that combined the chatbot system and tourism service. The chatbot curator will develop into a form of inducing interest and curiosity to users through learning, and then facilitating the desire for tourism. The purpose of this study is to lay the foundation for a chatbot curator based on previous studies.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.843-848
• /
• 2022

A chatbot is a responsive chatting program that can communicate with people through text or voice. 'Siri' and 'Bixby' installed in smartphones are also representative artificial intelligences that use the chatbot system. With the rapid development of chatbots, users in various fields have also begun to pay attention to the food service industry. As machine learning technology developed, it became possible to use more flexible conversations, and it soon expanded to the realm of education. Userㄴs interact through conversations with chatbots, and active interactions stimulate users' desires and at the same time have a positive effect on learning motivation. Recommendation system programs using chatbots not only recommend products according to users' preferences, but also provide various additional information. This study planned a program that combined the chatbot system and tourism service. The chatbot curator will develop into a form of inducing interest and curiosity to users through learning, and then facilitating the desire for tourism. The purpose of this study is to lay the foundation for a chatbot curator based on previous studies.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.333-338
• /
• 2006

최근 사용자에 대한 많은 정보를 얻는 것이 가능해지면서, 데이터마이닝 기법이나 Contents 추천 기법을 이용한 맞춤형 서비스가 가능하게 되었다. 특히, 대부분의 사람들에게 TV 프로그램 시청은 여가생활시간에서 가장 높은 비중을 차지 하고 있다. 따라서, 보다 지능적인 TV 프로그램 서비스를 제공하는 기술에 대하여 관심이 고조되고 있다. 본 논문에서는 TV-Anytime을 이용하여 개인화된 Electronic Program Guide (EPG)를 생성하고, 개인화된 EPG 정보를 활용하여 시청자에게 맞춤형 TV 프로그램 서비스를 제공하는 시스템에 대한 연구 결과를 제시한다. 또한 시청자의 시청패턴과 TV 프로그램 선호도를 바탕으로 시청자가 원하는 프로그램을 추천하는 TV Program Recommender Agent와 방송 및 TV 프로그램에 대한 대화를 담당하는 TV Program Helper Agent, 시스템 조정 및 메시지 전달을 담당하는 Coordinator Agent로 이루어진 멀티에이전트 기반 시스템 구조를 제시한다.